[LoRA] support non-diffusers LTX-Video loras

[linoytsaban]

for testing (more available LoRA here):

• LoRAs for LTX-video 0.9.7 13B work with LTXV 0.9.7 distilled

import torch
from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition
from diffusers.utils import export_to_video, load_video

pipe = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.7-distilled", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("Lightricks/LTXV-LoRAs", weight_name="bullet_time_step_02250_comfy.safetensors")
pipe.to("cuda")
pipe.vae.enable_tiling()

prompt = "bullet-time, artistic anatomical 3d render, utlra quality, human half full male body with transparent skin revealing structure instead of organs, muscular, intricate creative patterns, monochromatic with backlighting, lightning mesh, scientific concept art, blending biology with botany, surreal and ethereal quality, unreal engine 5, ray tracing, ultra realistic, 16K UHD, rich details."
negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
height, width = 480, 832
num_frames = 121

video = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=width,
    height=height,
    num_frames=num_frames,
    guidance_scale=1.0,
    num_inference_steps=10,
    decode_timestep=0.05,
    decode_noise_scale=0.025,
    generator=torch.Generator().manual_seed(42),
).frames[0]
export_to_video(video, "output5.mp4", fps=24)

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[sayakpaul]

Just two minor suggestions. Thank you!

[linoytsaban]

@bot /style

[github-actions]

Style fixes have been applied. View the workflow run here.